2026-09论文中文摘要
反事实脆弱性证书：结构化证据失效下的高置信度脆弱性暴露
Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure
arXiv 2609.00366 · 2026-09-02Dr. Claw：用于氛围研究的AI科学家工作空间
Dr. Claw: An AI Scientist Workspace for Vibe Research
arXiv 2609.00365 · 2026-09-02闭式解与合成孪生体：从嵌入统计量预测近似最近邻召回率
Closed Forms and Synthetic Twins: Predicting Approximate Nearest Neighbor Recall from Embedding Statistics
arXiv 2609.00364 · 2026-09-02跨GPU内核的确定性大语言模型推理：二的幂次INT8量化尺度与基于容忍度的一致性极限
Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance
arXiv 2609.00363 · 2026-09-02重新审视反馈驱动的大语言模型（LLM）代码修复：一项复现及探索性Java扩展研究
Revisiting Feedback-Driven LLM Code Repair: A Replication and Exploratory Java Extension
arXiv 2609.00362 · 2026-09-02净化有毒交流：负责任人工智能的设计科学方法
Detoxifying Toxic Communication: A Design Science Approach to Responsible AI
arXiv 2609.00361 · 2026-09-02利用Fe₈单分子磁体改进单分子磁体中粒子诱导磁雪崩的阈值
Improved Threshold for Particle-Induced Magnetic Avalanche in Single-Molecule Magnets Using Fe$_8$ Molecule
arXiv 2609.00360 · 2026-09-02用于参数化超弹性的多凸神经势混合模型：迈向基础材料模型
Mixture of Polyconvex Neural Potentials for Parametric Hyperelasticity: Towards Foundation Material Models
arXiv 2609.00359 · 2026-09-02经验应存储在何处？用于持续视觉Transformer的分层赫布记忆
Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers
arXiv 2609.00358 · 2026-09-02加拿大银河辐射测绘仪（CGEM）：一项宇宙微波前景实验
The Canadian Galactic Emission Mapper (CGEM): A Cosmic Microwave Foreground Experiment
arXiv 2609.00357 · 2026-09-02一种用于量子联邦学习的稳定聚合方法
A Stable Aggregation Method for Quantum Federated Learning
arXiv 2609.00356 · 2026-09-02探索研究与实践中的量子软件测试：多视角文献综述的新兴成果
Exploring Quantum Software Testing Across Research and Practice: Emerging Results from a Multivocal Literature Review
arXiv 2609.00354 · 2026-09-02微分形式的拓扑诱导形变
Topologically induced deformations of differential forms
arXiv 2609.00353 · 2026-09-02LGBTQIA+身份如何影响大语言模型的行为？对心理健康AI系统需求工程的启示
How Does LGBTQIA+ Identity Affect LLM Behavior? Implications for Requirements Engineering of Mental Health AI Systems
arXiv 2609.00352 · 2026-09-02通过激活匹配微调检测大语言模型中的隐藏行为
Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning
arXiv 2609.00351 · 2026-09-02边界断点设计中的操纵检验
Manipulation Testing in Boundary Discontinuity Designs
arXiv 2609.00350 · 2026-09-02通过横向里德伯阻塞相互作用的光子的空间关联
Spatial correlations of photons interacting via transverse Rydberg blockade
arXiv 2609.00348 · 2026-09-02紧李群对偶的直极限完备化中的代数对象与c=1顶点算子代数的分类
Algebra objects in direct limit completions of compact Lie group duals and the classification of $c=1$ vertex operator algebras
arXiv 2609.00347 · 2026-09-02AniMaster：通过电影脚本生成与交互式创作从故事文本制作动画视频
AniMaster: From Story Texts to Animated Videos via Cinematic Script Generation and Interactive Authoring
arXiv 2609.00346 · 2026-09-02大型语言模型（LLM）是否了解你的社区？审计LLM先验以用于社区层面的流动性预测与结构对齐
Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment
arXiv 2609.00345 · 2026-09-02从工具使用到技术能动性：LoopCAT——一款面向翻译技术教育的本地优先开源工具
From Tool Use to Technological Agency: LoopCAT as a Local-First, Open-Source Tool for Translation Technology Education
arXiv 2609.00344 · 2026-09-02SlideBank：用于一致全切片推理的持久分层证据库
SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
arXiv 2609.00342 · 2026-09-02用于相干X射线成像的多图像重叠拼接与自动图像构建
Multi-image Overlap Stitching and Automatic Image Construction for Coherent X-ray Imaging
arXiv 2609.00341 · 2026-09-02OreProof：使用零知识证明实现关键矿产供应链的有限披露可验证溯源
OreProof: Verifiable Provenance with Limited Disclosure for Critical-Minerals Supply Chains Using Zero-Knowledge Proofs
arXiv 2609.00340 · 2026-09-02二维平带超导体中依赖于杂质的量子几何
Impurity-dependent quantum geometry in 2D flat band superconductors
arXiv 2609.00338 · 2026-09-02体积、直径与Cheeger常数的Blaschke–Santaló图
Blaschke--Santal{ó} diagram for the volume, the diameter, and the Cheeger constant
arXiv 2609.00337 · 2026-09-02沿直线的点电荷势的临界点
Critical points of point charge potentials along lines
arXiv 2609.00336 · 2026-09-02面向负责任AI的人机协同解释：一种解释学视角
Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective
arXiv 2609.00334 · 2026-09-02面向自动驾驶 ego 中心数据集的基于场景图的驾驶场景提取
Scene Graph-based Driving Scenario Extraction for Automotive Egocentric Datasets
arXiv 2609.00333 · 2026-09-02用于隐含波动率曲面的生成模型的隐空间无套利几何
Latent-Space No-Arbitrage Geometry of Generative Models for Implied Volatility Surfaces
arXiv 2609.00332 · 2026-09-02用微流变学研究动力学异质性
Using microrheology to study dynamical heterogeneities
arXiv 2609.00331 · 2026-09-02野外场景下的主题匹配：来自真实世界ASR转录文本的基准与经验教训
Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
arXiv 2609.00330 · 2026-09-02词汇规范化中的多语言诅咒
The Curse of Multilinguality in Lexical Normalization
arXiv 2609.00329 · 2026-09-02三矩阵模型中模糊球的吸积、合并与亚稳态
Accretion, mergers, and metastability of fuzzy spheres in a three-matrix model
arXiv 2609.00328 · 2026-09-02基于智能体框架的流动性与能源政策建模：以2050年芝加哥地区为例
Modeling of Mobility and Energy Policies in an Agent-Based Framework: Case Studies for Chicago Region in 2050
arXiv 2609.00327 · 2026-09-02关于全纯向量丛上埃尔米特度量的一种构造
On a construction of hermitian metrics on holomorphic vector bundles
arXiv 2609.00326 · 2026-09-02多语言语言模型中语言控制的潜在机制
Latent Mechanisms of Language Control in Multilingual Language Models
arXiv 2609.00325 · 2026-09-02分数Yamabe极小化子的定量稳定性
Quantitative Stability for Fractional Yamabe minimizers
arXiv 2609.00324 · 2026-09-02大型语言模型是否偏向特定研究主题？
Do Large Language Models Favour Any Research Topics?
arXiv 2609.00323 · 2026-09-02社交网络上的微生物组动态建模：宿主间传播如何塑造宿主体内进化
Modeling microbiome dynamics on social networks: how between-host transmission shapes within-host evolution
arXiv 2609.00320 · 2026-09-02信息源：针对AI心理健康信息查询中引用的多平台多语言审计
Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries
arXiv 2609.00319 · 2026-09-02极冠冕洞类太阳风在加速阶段的直接测量
Direct Measurement of Polar Coronal Hole-like Solar Wind in its Acceleration Phase
arXiv 2609.00318 · 2026-09-02基于热力学第二定律的无鬼高阶梯度牛顿引力
Ghost-free higher-gradient Newtonian gravity from the Second Law of Thermodynamics
arXiv 2609.00317 · 2026-09-02通用3R机器人的几何分析，以及一类正交机器人具有四个逆运动学解（IKS）的充要条件
Geometric analysis of generic 3R robots, and necessary and sufficient conditions for a class of orthogonal robots to have four IKS
arXiv 2609.00316 · 2026-09-02无界域上带点相互作用的Robin拉普拉斯算子：离散谱与耦合渐近行为
Robin Laplacians with point interactions on unbounded domains: discrete spectrum and coupling asymptotics
arXiv 2609.00315 · 2026-09-02关于大覆盖与强闭离散游戏
On Large Covers and the Strong Closed Discrete Game
arXiv 2609.00314 · 2026-09-02MUSES：前瞻性知识根源检索基准
MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval
arXiv 2609.00313 · 2026-09-02带点曲线的合冲（Syzygies）
Weighted Syzygies of Pointed Curves
arXiv 2609.00312 · 2026-09-02通用3R位置机器人的逆运动学求解：共形几何代数方法
Inverse kinematic solution for generic 3R positional robots using Conformal Geometric Algebra
arXiv 2609.00311 · 2026-09-02大语言模型角色中的情绪劳动策略偏好
Emotional Labor Strategy Preferences in LLM Personas
arXiv 2609.00310 · 2026-09-02
